Related papers: Advantage-based Temporal Attack in Reinforcement L…
Dialogue systems are usually built on either generation-based or retrieval-based approaches, yet they do not benefit from the advantages of different models. In this paper, we propose a Retrieval-Enhanced Adversarial Training (REAT) method…
Adversarial training (AT) is a popular method for training robust deep neural networks (DNNs) against adversarial attacks. Yet, AT suffers from two shortcomings: (i) the robustness of DNNs trained by AT is highly intertwined with the size…
Transfer adversarial attack is a non-trivial black-box adversarial attack that aims to craft adversarial perturbations on the surrogate model and then apply such perturbations to the victim model. However, the transferability of…
Adversarial attacks in reinforcement learning (RL) often assume highly-privileged access to the victim's parameters, environment, or data. Instead, this paper proposes a novel adversarial setting called a Cheap Talk MDP in which an…
In this paper, we propose Inverse Adversarial Training (IAT) algorithm for training neural dialogue systems to avoid generic responses and model dialogue history better. In contrast to standard adversarial training algorithms, IAT…
We propose an adversarial deep reinforcement learning (ADRL) algorithm for high-dimensional stochastic control problems. Inspired by the information relaxation duality, ADRL reformulates the control problem as a min-max optimization between…
Recently proposed adversarial training methods show the robustness to both adversarial and original examples and achieve state-of-the-art results in supervised and semi-supervised learning. All the existing adversarial training methods…
Deep Reinforcement Learning (DRL) policies have been shown to be vulnerable to small adversarial noise in observations. Such adversarial noise can have disastrous consequences in safety-critical environments. For instance, a self-driving…
Deep Reinforcement Learning (DRL) is a subfield of machine learning for training autonomous agents that take sequential actions across complex environments. Despite its significant performance in well-known environments, it remains…
This paper proposes a classification framework with a rejection option to mitigate the performance deterioration caused by adversarial examples. While recent machine learning algorithms achieve high prediction performance, they are…
Decision Transformer (DT), which employs expressive sequence modeling techniques to perform action generation, has emerged as a promising approach to offline policy optimization. However, DT generates actions conditioned on a desired future…
Advancements in reinforcement learning (RL) have been remarkable in recent years. However, the limitations of traditional training methods have become increasingly evident, particularly in meta-RL settings where agents face new, unseen…
Deep neural networks (DNNs) have achieved remarkable performance in many tasks, yet they often behave as opaque black boxes. Explanation-guided learning (EGL) methods steer DNNs using human-provided explanations or supervision on model…
Deep neural networks are highly vulnerable to adversarial examples, i.e.,small perturbations that can significantly degrade model performance. While adversarial training has become the primary defense strategy, most studies focus on…
We study the robustness of reinforcement learning (RL) with adversarially perturbed state observations, which aligns with the setting of many adversarial attacks to deep reinforcement learning (DRL) and is also important for rolling out…
Reinforcement learning (RL) enables sequential decision-making in complex and high-dimensional environments through interaction with the environment. In most real-world applications, however, a high number of interactions are infeasible. In…
Deep Neural Networks (DNNs) are widely acknowledged to be susceptible to adversarial examples, wherein imperceptible perturbations are added to clean examples through diverse input transformation attacks. However, these methods originally…
Components of cyber physical systems, which affect real-world processes, are often exposed to the internet. Replacing conventional control methods with Deep Reinforcement Learning (DRL) in energy systems is an active area of research, as…
The neural network (NN) becomes one of the most heated type of models in various signal processing applications. However, NNs are extremely vulnerable to adversarial examples (AEs). To defend AEs, adversarial training (AT) is believed to be…
Deep learning has achieved great success in computer vision, but remains vulnerable to adversarial attacks. Adversarial training is the leading defense designed to improve model robustness. However, its effect on the transferability of…